Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Crossformer× | Informer× | PatchTST× | |
|---|---|---|---|
| Obor | Hluboké učení | Hluboké učení | Hluboké učení |
| Rodina | Machine learning | Machine learning | Machine learning |
| Rok vzniku≠ | 2023 | 2021 | 2023 |
| Tvůrce≠ | Yunhao Zhang & Junchi Yan | Zhou, H. et al. | Nie, Y. et al. |
| Typ≠ | Transformer-based multivariate time-series forecasting model | Transformer (ProbSparse self-attention) | Transformer for time series forecasting |
| Původní zdroj≠ | Zhang, Y., & Yan, J. (2023). Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. ICLR. link ↗ | Zhou, H. et al. (2021). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. AAAI. DOI ↗ | Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR. link ↗ |
| Další názvy | Cross-Dimension Dependency Transformer, Crossformer TSF, Çapraz-Boyut Bağımlılık Transformatörü | Informer — Uzun Dizi Transformer Tahmini, Informer transformer, ProbSparse attention forecaster | PatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer |
| Příbuzné≠ | 3 | 5 | 3 |
| Shrnutí≠ | Crossformer is a Transformer-based architecture for multivariate time series forecasting, introduced by Yunhao Zhang and Junchi Yan at ICLR 2023. Unlike earlier Transformer variants that treat each variate independently, Crossformer explicitly models cross-dimension dependencies alongside temporal patterns. It achieves this through a two-stage attention design — cross-time and cross-dimension — applied over segment-level embeddings organized in a hierarchical encoder, enabling the model to capture both intra-variate dynamics and inter-variate correlations simultaneously. | Informer is a Transformer-based model introduced by Zhou et al. in 2021 for long-sequence time-series forecasting, using a ProbSparse self-attention mechanism that lowers the computational complexity of the standard Transformer to O(L log L). It is built for problems that demand predictions across thousands of future steps. | PatchTST is a patch-based Transformer architecture for time series forecasting, introduced by Nie and colleagues in 2023, that cuts each series into overlapping patches treated as tokens and processes channels independently. It balances computational efficiency with strong accuracy on long-horizon forecasting. |
| ScholarGateDatová sada ↗ |
|
|
|